Michael F. MBOUOPDA

Michael F. MBOUOPDA

Machine Learning Researcher

Huawei Technologies (Ireland)

Biography

I am a machine learning researcher at Huawei Technologies, affected at the Ireland Intelligent Operation & Management Lab.

I am interested in Machine Learning and Artificial Intelligence in general. Currently, I am working on building efficient and explainable machine learning models to help achieve the Autonomous Driving Network (ADN).

Interests
  • Time Series Analysis
  • Machine Learning
  • Deep Learning
  • Artificial Intelligence
  • Explainable Artificial Intelligence
  • Martial Arts
Education
  • PhD in Machine Learning, from Oct 2019 to Dec 2022

    LIMOS, University of Clermont Auvergne

  • Master of computer Science, from Sep 2018 to Sep 2019

    University of Clermont Auvergne

  • Master of Computer Science, from Sep 2016 to Sep 2018

    University of Yaounde 1

Skills

chip
Machine/Deep Learning

90%

Python

90%

pytorch
Pytorch

90%

tensorflow
TensorFlow

90%

Analytics

90%

Java

90%

Experience

 
 
 
 
 
Machine Learning Researcher
December 2022 – Present Dublin, Ireland
Use machine learning to achieve the Autonomous Driving Network (ADN). This position implies techniques such as time series analysis, anomaly detection and explainable artificial intelligence.
 
 
 
 
 
Machine Learning Researcher
October 2019 – October 2022 Aubiere, France
Design and build innovative algorithms for the analysis of uncertain time series. The first step focuses on the classification of uncertain time series.
 
 
 
 
 
Machine Learning Junior Researcher
April 2019 – September 2019 Aubiere, France
Develop a new shapelet algorithm for the classification of uncertain time series data. Here I used the techniques of uncertainty propagation and adapted the well known and appreciated Shapelet Transform algorithm to the context of uncertain time series classification. This experience has succesfully ended with a communication at the Learning From Data Stream and Time Series workshop
 
 
 
 
 
Machine Learning Junior Researcher
Department of Computer Science - University of Yaounde I
June 2017 – September 2018 Yaounde, Cameroon
Design and build a novel framework for named entity recognition in low-resource languages. In this experience, I build a novel approach using distributional word representation coupled to neural network
 
 
 
 
 
Applied Researcher
Ibaas Labs
June 2016 – September 2019 Yaounde, Cameroon

I worked in a team in order to:

  1. Build a professional social network to improve job delivery. The system must help project owners to quickly find the best experts for their job. For experts, the system must help them find the most appropriate tools given a job.

  2. Build an entertainment social network application.

We have developed the android application Jooka and a Software Delivery Engine platform.

Accomplish­ments

Microsoft Azure Data Scientist Associate (DP-100) Professional Certificate
Apply data science and machine learning to implement and run machine learning workloads on Azure.
See certificate
Mathematics for Machine Learning and Data Science Specialization
Master the Toolkit of AI and Machine Learning. Mathematics for Machine Learning and Data Science is a beginner-friendly Specialization where you’ll learn the fundamental mathematics toolkit of machine learning: calculus, linear algebra, statistics, and probability.
See certificate
Deep Learning Specialization
In five courses, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more. You will work on case studies from healthcare, autonomous driving, sign language reading, music generation, and natural language processing. You will master not only the theory, but also see how it is applied in industry. You will practice all these ideas in Python and in TensorFlow, which we will teach.
See certificate
Research integrity in scientific professions
Learn the integrity principles (Reliability, Honesty, Respect and Responsibility) that must gouvern any scientific reasearch
See certificate
Practical Time Series Analysis
This course starts by teaching the stochastic processes behind any time series. I have learnt to estimate the parameters of such stochastic processes. I have finally learnt time series analysis models MA(q), AR(p), ARMA(p,q), ARIMA(p,q,d), SARIMA(p,q,d,s) and Holt-Winters, and applied them on different datasets using the R programming language
Intro to TensorFlow for Deep Learning
A practical introduction to deep learning using tensorflow. In this course, I learnt how do feedforward neural network, convotional neural network and recurrent neural network work. I have also learnt about data augmentation and time series forecasting. I use the Kera api through tensorflow to build all my models
Reproducible Research: Methodological Principles for Transparent Science
In this course, I have enjoyed learning about reproducibility in science. And also, about the importance of transparent science. After this course, I was able to correctly share all the necessary materials in order to let anyone to reproduce my work
See certificate
Coursera
Machine Learning
I discovered Machine Learning with this course, taught by the amazing professor Andrew Ng. I have learnt the fundamental of machine learning. I have learnt regression, classification and clustering models. I have also studied anomaly detection and recommender systems.

Projects

*
Taekwondo Kicks Prediction Using Time Series of Poses
In this project, we built a machine learning framework to accurately recognize taekwondo moves. Each moves is modelled as a time series of poses. The poses are captured with the help of the PoseNet deep neural network running on a mobile phone. Once the poses are captured, they are sent to a remote server which performs the move prediction and return the results to the phone.
Taekwondo Kicks Prediction Using Time Series of Poses
MonPoulailler (The famer’s intelligent assistant)
An android application that allows chicken farmers to manage their business and improve their profitability with the utmost simplicity. MyPoulailler allows you to manage the stock of chickens, the dead, the food, the sales, the medicines, the farmers and all the other aspects of raising chickens using your phone.
MonPoulailler (The famer's intelligent assistant)